Research map / Image generation / Super-resolution
Practical Single-Image Super-Resolution Using Look-Up Table
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace bicubic interpolation with SR-LUT Ours-V | Single-image ×4 super-resolution · Set5 | PSNR: 28.42 -> 29.22 | Helped |
| Replace bicubic interpolation with SR-LUT Ours-F | Single-image ×4 super-resolution · Set5 | PSNR: 28.42 -> 29.77 | Helped |
| Replace bicubic interpolation with SR-LUT Ours-S | Single-image ×4 super-resolution · Set5 | runtime: 60ms -> 91ms | Hurt |
| Use Ours-V instead of bicubic interpolation | Single-image ×4 super-resolution · Samsung Galaxy S7, 1280 × 720 output | runtime: 60ms -> 15ms | Helped |
| Use Ours-F instead of bicubic interpolation | Single-image ×4 super-resolution · Samsung Galaxy S7, 1280 × 720 output | runtime: 60ms -> 34ms | Helped |
| Add rotational ensemble training (ablation) | Ours-S · Set5 | PSNR: 28.32 -> 29.82 | Helped |
| Use an asymmetric 1 × 3 kernel instead of a symmetric 1 × 3 kernel (ablation) | SR-LUT · Set5 | PSNR: 27.75 -> 29.77 | Helped |
| Expand the receptive field from size 2 to size 3 (ablation) | SR-LUT · Set5 | PSNR: 29.22 -> 29.77 | Helped |
| Increase sampling interval from 24 to 25 (ablation) | Ours-S · Set5 | PSNR: 29.82 -> 29.62 | Hurt |
| Increase sampling interval from 24 to 26 (ablation) | Ours-S · Set5 | PSNR: 29.82 -> 29.18 | Hurt |
Closest papers by meaning
- Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution (AAAI 2024 · similarity 0.91)
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016 · similarity 0.89)
- Explorable Super Resolution (CVPR 2020 · similarity 0.87)
- “Zero-Shot” Super-Resolution Using Deep Internal Learning (CVPR 2018 · similarity 0.87)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.86)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.